From 11246c708acdfa9512d7b69c18938810c20fd6ab Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 21 Oct 2014 17:29:02 -0300 Subject: perf tools: Set thread->mg.machine in all places We were setting this only in machine__init(), i.e. for the map_groups that holds the kernel module maps, not for the one used for a thread's executable mmaps. Now we are sure that we can obtain the machine where a thread is by going via thread->mg->machine, thus we can, in the following patch, make all codepaths that receive machine _and_ thread, drop the machine one. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jean Pihet Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-y6zgaqsvhrf04v57u15e4ybm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 34fc7c8672e4..c70b3ff7b289 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -21,7 +21,7 @@ static void dsos__init(struct dsos *dsos) int machine__init(struct machine *machine, const char *root_dir, pid_t pid) { - map_groups__init(&machine->kmaps); + map_groups__init(&machine->kmaps, machine); RB_CLEAR_NODE(&machine->rb_node); dsos__init(&machine->user_dsos); dsos__init(&machine->kernel_dsos); @@ -32,7 +32,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->vdso_info = NULL; - machine->kmaps.machine = machine; machine->pid = pid; machine->symbol_filter = NULL; @@ -319,7 +318,7 @@ static void machine__update_thread_pid(struct machine *machine, goto out_err; if (!leader->mg) - leader->mg = map_groups__new(); + leader->mg = map_groups__new(machine); if (!leader->mg) goto out_err; -- cgit v1.2.3 From bb871a9c8d68692ed2513b3f0e1c010c2ac12f44 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 23 Oct 2014 12:50:25 -0300 Subject: perf tools: A thread's machine can be found via thread->mg->machine So stop passing both machine and thread to several thread methods, reducing function signature length. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jean Pihet Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-ckcy19dcp1jfkmdihdjcqdn1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/powerpc/util/skip-callchain-idx.c | 5 ++-- tools/perf/builtin-inject.c | 3 +- tools/perf/builtin-script.c | 7 ++--- tools/perf/builtin-timechart.c | 2 +- tools/perf/builtin-trace.c | 6 ++-- tools/perf/tests/code-reading.c | 3 +- tools/perf/tests/mmap-thread-lookup.c | 2 +- tools/perf/util/build-id.c | 3 +- tools/perf/util/callchain.h | 6 ++-- tools/perf/util/event.c | 19 ++++++------ tools/perf/util/event.h | 1 - tools/perf/util/machine.c | 35 +++++++++-------------- tools/perf/util/thread.c | 4 +-- tools/perf/util/thread.h | 5 ++-- tools/perf/util/unwind-libdw.c | 4 +-- tools/perf/util/unwind-libunwind.c | 13 ++++----- 16 files changed, 48 insertions(+), 70 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 9892b0f0bec4..3bb50eac5542 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -232,8 +232,7 @@ out: * index: of callchain entry that needs to be ignored (if any) * -1 if no entry needs to be ignored or in case of errors */ -int arch_skip_callchain_idx(struct machine *machine, struct thread *thread, - struct ip_callchain *chain) +int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) { struct addr_location al; struct dso *dso = NULL; @@ -246,7 +245,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread, ip = chain->ips[2]; - thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER, + thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); if (al.map) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index de99ca1bb942..06f1758951f1 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -217,8 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, goto repipe; } - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->ip, &al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al); if (al.map != NULL) { if (!al.map->dso->hit) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9708a1290571..b35517f2ceb5 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -379,7 +379,6 @@ static void print_sample_start(struct perf_sample *sample, static void print_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct perf_event_attr *attr) { @@ -390,7 +389,7 @@ static void print_sample_addr(union perf_event *event, if (!sample_addr_correlates_sym(attr)) return; - perf_event__preprocess_sample_addr(event, sample, machine, thread, &al); + perf_event__preprocess_sample_addr(event, sample, thread, &al); if (PRINT_FIELD(SYM)) { printf(" "); @@ -438,7 +437,7 @@ static void print_sample_bts(union perf_event *event, ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && !output[attr->type].user_set)) { printf(" => "); - print_sample_addr(event, sample, al->machine, thread, attr); + print_sample_addr(event, sample, thread, attr); } if (print_srcline_last) @@ -475,7 +474,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample, event_format__print(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size); if (PRINT_FIELD(ADDR)) - print_sample_addr(event, sample, al->machine, thread, attr); + print_sample_addr(event, sample, thread, attr); if (PRINT_FIELD(IP)) { if (!symbol_conf.use_callchain) diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 35b425b6293f..f5fb256d90d5 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -528,7 +528,7 @@ static const char *cat_backtrace(union perf_event *event, } tal.filtered = 0; - thread__find_addr_location(al.thread, machine, cpumode, + thread__find_addr_location(al.thread, cpumode, MAP__FUNCTION, ip, &tal); if (tal.sym) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index fb126459b134..83a4835c8118 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1846,7 +1846,7 @@ static int trace__pgfault(struct trace *trace, if (trace->summary_only) return 0; - thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION, + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, sample->ip, &al); trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output); @@ -1859,11 +1859,11 @@ static int trace__pgfault(struct trace *trace, fprintf(trace->output, "] => "); - thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE, + thread__find_addr_location(thread, cpumode, MAP__VARIABLE, sample->addr, &al); if (!al.map) { - thread__find_addr_location(thread, trace->host, cpumode, + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, sample->addr, &al); if (al.map) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 67f2d6323558..144a41236456 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -145,8 +145,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr, - &al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); if (!al.map || !al.map->dso) { pr_debug("thread__find_addr_map failed\n"); return -1; diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 4a456fef66ca..2113f1c8611f 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -187,7 +187,7 @@ static int mmap_events(synth_cb synth) pr_debug("looking for map %p\n", td->map); - thread__find_addr_map(thread, machine, + thread__find_addr_map(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, (unsigned long) (td->map + 1), &al); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index a904a4cfe7d3..2e7c68e39330 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -33,8 +33,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, return -1; } - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->ip, &al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al); if (al.map != NULL) al.map->dso->hit = 1; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 94cfefddf4db..3caccc2c173c 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -184,11 +184,9 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest, } #ifdef HAVE_SKIP_CALLCHAIN_IDX -extern int arch_skip_callchain_idx(struct machine *machine, - struct thread *thread, struct ip_callchain *chain); +extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain); #else -static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused, - struct thread *thread __maybe_unused, +static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, struct ip_callchain *chain __maybe_unused) { return -1; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 4af6b279e34a..e00a29fb099f 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -730,12 +730,12 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, return machine__process_event(machine, event, sample); } -void thread__find_addr_map(struct thread *thread, - struct machine *machine, u8 cpumode, +void thread__find_addr_map(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { struct map_groups *mg = thread->mg; + struct machine *machine = mg->machine; bool load_map = false; al->machine = machine; @@ -806,14 +806,14 @@ try_again: } } -void thread__find_addr_location(struct thread *thread, struct machine *machine, +void thread__find_addr_location(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { - thread__find_addr_map(thread, machine, cpumode, type, addr, al); + thread__find_addr_map(thread, cpumode, type, addr, al); if (al->map != NULL) al->sym = map__find_symbol(al->map, al->addr, - machine->symbol_filter); + thread->mg->machine->symbol_filter); else al->sym = NULL; } @@ -842,8 +842,7 @@ int perf_event__preprocess_sample(const union perf_event *event, machine->vmlinux_maps[MAP__FUNCTION] == NULL) machine__create_kernel_maps(machine); - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->ip, al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : ""); @@ -902,16 +901,14 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void perf_event__preprocess_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct addr_location *al) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - sample->addr, al); + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al); if (!al->map) - thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE, + thread__find_addr_map(thread, cpumode, MAP__VARIABLE, sample->addr, al); al->cpu = sample->cpu; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 5699e7e2a790..5f0e0b89e130 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -322,7 +322,6 @@ bool is_bts_event(struct perf_event_attr *attr); bool sample_addr_correlates_sym(struct perf_event_attr *attr); void perf_event__preprocess_sample_addr(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct thread *thread, struct addr_location *al); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c70b3ff7b289..08e63fdbd14f 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1289,7 +1289,7 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex) return 0; } -static void ip__resolve_ams(struct machine *machine, struct thread *thread, +static void ip__resolve_ams(struct thread *thread, struct addr_map_symbol *ams, u64 ip) { @@ -1303,7 +1303,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, * Thus, we have to try consecutively until we find a match * or else, the symbol is unknown */ - thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al); + thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al); ams->addr = ip; ams->al_addr = al.addr; @@ -1311,23 +1311,21 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, ams->map = al.map; } -static void ip__resolve_data(struct machine *machine, struct thread *thread, +static void ip__resolve_data(struct thread *thread, u8 m, struct addr_map_symbol *ams, u64 addr) { struct addr_location al; memset(&al, 0, sizeof(al)); - thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, - &al); + thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al); if (al.map == NULL) { /* * some shared data regions have execute bit set which puts * their mapping in the MAP__FUNCTION type array. * Check there as a fallback option before dropping the sample. */ - thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr, - &al); + thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al); } ams->addr = addr; @@ -1344,9 +1342,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, if (!mi) return NULL; - ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip); - ip__resolve_data(al->machine, al->thread, al->cpumode, - &mi->daddr, sample->addr); + ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); + ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr); mi->data_src.val = sample->data_src; return mi; @@ -1363,15 +1360,14 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, return NULL; for (i = 0; i < bs->nr; i++) { - ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to); - ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from); + ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from); bi[i].flags = bs->entries[i].flags; } return bi; } -static int machine__resolve_callchain_sample(struct machine *machine, - struct thread *thread, +static int thread__resolve_callchain_sample(struct thread *thread, struct ip_callchain *chain, struct symbol **parent, struct addr_location *root_al, @@ -1395,7 +1391,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. */ - skip_idx = arch_skip_callchain_idx(machine, thread, chain); + skip_idx = arch_skip_callchain_idx(thread, chain); for (i = 0; i < chain_nr; i++) { u64 ip; @@ -1437,7 +1433,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, } al.filtered = 0; - thread__find_addr_location(thread, machine, cpumode, + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, ip, &al); if (al.sym != NULL) { if (sort__has_parent && !*parent && @@ -1476,11 +1472,8 @@ int machine__resolve_callchain(struct machine *machine, struct addr_location *root_al, int max_stack) { - int ret; - - ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent, - root_al, max_stack); + int ret = thread__resolve_callchain_sample(thread, sample->callchain, + parent, root_al, max_stack); if (ret) return ret; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 8db9626f6835..bf5bf858b7f6 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -198,7 +198,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) } void thread__find_cpumode_addr_location(struct thread *thread, - struct machine *machine, enum map_type type, u64 addr, struct addr_location *al) { @@ -211,8 +210,7 @@ void thread__find_cpumode_addr_location(struct thread *thread, }; for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { - thread__find_addr_location(thread, machine, cpumodes[i], type, - addr, al); + thread__find_addr_location(thread, cpumodes[i], type, addr, al); if (al->map) break; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 8c75fa774706..6ef9fe6ff8da 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -54,16 +54,15 @@ void thread__insert_map(struct thread *thread, struct map *map); int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); -void thread__find_addr_map(struct thread *thread, struct machine *machine, +void thread__find_addr_map(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); -void thread__find_addr_location(struct thread *thread, struct machine *machine, +void thread__find_addr_location(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); void thread__find_cpumode_addr_location(struct thread *thread, - struct machine *machine, enum map_type type, u64 addr, struct addr_location *al); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 7419768c38b1..f24b350ab192 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -26,7 +26,7 @@ static int __report_module(struct addr_location *al, u64 ip, Dwfl_Module *mod; struct dso *dso = NULL; - thread__find_addr_location(ui->thread, ui->machine, + thread__find_addr_location(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, al); @@ -89,7 +89,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, struct addr_location al; ssize_t size; - thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, addr, &al); if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 4d45c0dfe343..29acc8cccb56 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -284,7 +284,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; - thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); return al.map; } @@ -374,7 +374,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, struct addr_location al; ssize_t size; - thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, addr, &al); if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); @@ -476,14 +476,13 @@ static void put_unwind_info(unw_addr_space_t __maybe_unused as, pr_debug("unwind: put_unwind_info called\n"); } -static int entry(u64 ip, struct thread *thread, struct machine *machine, +static int entry(u64 ip, struct thread *thread, unwind_entry_cb_t cb, void *arg) { struct unwind_entry e; struct addr_location al; - thread__find_addr_location(thread, machine, - PERF_RECORD_MISC_USER, + thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); e.ip = ip; @@ -586,7 +585,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, unw_word_t ip; unw_get_reg(&c, UNW_REG_IP, &ip); - ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0; + ret = ip ? entry(ip, ui->thread, cb, arg) : 0; } return ret; @@ -611,7 +610,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (ret) return ret; - ret = entry(ip, thread, machine, cb, arg); + ret = entry(ip, thread, cb, arg); if (ret) return -ENOMEM; -- cgit v1.2.3 From cc8b7c2bf553151a579a8009020875faa1d43e29 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 23 Oct 2014 15:26:17 -0300 Subject: perf thread: Adopt resolve_callchain method from machine Shortening function signature lenght too, since a thread's machine can be obtained from thread->mg->machine, no need to pass thread, machine. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jean Pihet Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-5wb6css280ty0cel5p0zo2b1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 4 ++-- tools/perf/util/machine.c | 15 +++++++-------- tools/perf/util/machine.h | 13 ++++++------- tools/perf/util/scripting-engines/trace-event-python.c | 6 +++--- tools/perf/util/session.c | 6 +++--- 5 files changed, 21 insertions(+), 23 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index c84d3f8dcb75..00229809a904 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -754,8 +754,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || sort__has_parent) { - return machine__resolve_callchain(al->machine, evsel, al->thread, - sample, parent, al, max_stack); + return thread__resolve_callchain(al->thread, evsel, sample, + parent, al, max_stack); } return 0; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 08e63fdbd14f..fd192e4885cc 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1464,13 +1464,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) entry->map, entry->sym); } -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent, - struct addr_location *root_al, - int max_stack) +int thread__resolve_callchain(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { int ret = thread__resolve_callchain_sample(thread, sample->callchain, parent, root_al, max_stack); @@ -1487,7 +1486,7 @@ int machine__resolve_callchain(struct machine *machine, (!sample->user_stack.size)) return 0; - return unwind__get_entries(unwind_entry, &callchain_cursor, machine, + return unwind__get_entries(unwind_entry, &callchain_cursor, thread->mg->machine, thread, sample, max_stack); } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2b651a7f5d0d..88ec74e18cbf 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -122,13 +122,12 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al); struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al); -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent, - struct addr_location *root_al, - int max_stack); +int thread__resolve_callchain(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack); /* * Default guest kernel is defined by parameter --guestkallsyms diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 496f21cadd97..25e5a238f1cb 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -312,9 +312,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (machine__resolve_callchain(al->machine, evsel, al->thread, - sample, NULL, NULL, - PERF_MAX_STACK_DEPTH) != 0) { + if (thread__resolve_callchain(al->thread, evsel, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); goto exit; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 6702ac28754b..776010844cdc 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1417,9 +1417,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, if (symbol_conf.use_callchain && sample->callchain) { struct addr_location node_al; - if (machine__resolve_callchain(al->machine, evsel, al->thread, - sample, NULL, NULL, - PERF_MAX_STACK_DEPTH) != 0) { + if (thread__resolve_callchain(al->thread, evsel, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; -- cgit v1.2.3 From dd8c17a5fe80148aab8844e8774cf341212a4eb1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 23 Oct 2014 16:42:19 -0300 Subject: perf callchains: Use thread->mg->machine The unwind__get_entries() already receives the thread parameter, from where it can obtain the matching machine structure, shorten the signature. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Don Zickus Cc: Frederic Weisbecker Cc: Jean Pihet Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-isjc6bm8mv4612mhi6af64go@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/dwarf-unwind.c | 18 +++++++++--------- tools/perf/util/machine.c | 2 +- tools/perf/util/unwind-libdw.c | 4 ++-- tools/perf/util/unwind-libunwind.c | 4 ++-- tools/perf/util/unwind.h | 2 -- 5 files changed, 14 insertions(+), 16 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index fc25e57f4a5d..ab28cca2cb97 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -59,7 +59,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) } __attribute__ ((noinline)) -static int unwind_thread(struct thread *thread, struct machine *machine) +static int unwind_thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -72,7 +72,7 @@ static int unwind_thread(struct thread *thread, struct machine *machine) goto out; } - err = unwind__get_entries(unwind_entry, &cnt, machine, thread, + err = unwind__get_entries(unwind_entry, &cnt, thread, &sample, MAX_STACK); if (err) pr_debug("unwind failed\n"); @@ -89,21 +89,21 @@ static int unwind_thread(struct thread *thread, struct machine *machine) } __attribute__ ((noinline)) -static int krava_3(struct thread *thread, struct machine *machine) +static int krava_3(struct thread *thread) { - return unwind_thread(thread, machine); + return unwind_thread(thread); } __attribute__ ((noinline)) -static int krava_2(struct thread *thread, struct machine *machine) +static int krava_2(struct thread *thread) { - return krava_3(thread, machine); + return krava_3(thread); } __attribute__ ((noinline)) -static int krava_1(struct thread *thread, struct machine *machine) +static int krava_1(struct thread *thread) { - return krava_2(thread, machine); + return krava_2(thread); } int test__dwarf_unwind(void) @@ -137,7 +137,7 @@ int test__dwarf_unwind(void) goto out; } - err = krava_1(thread, machine); + err = krava_1(thread); out: machine__delete_threads(machine); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index fd192e4885cc..51a630301afa 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1486,7 +1486,7 @@ int thread__resolve_callchain(struct thread *thread, (!sample->user_stack.size)) return 0; - return unwind__get_entries(unwind_entry, &callchain_cursor, thread->mg->machine, + return unwind__get_entries(unwind_entry, &callchain_cursor, thread, sample, max_stack); } diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index f24b350ab192..2dcfe9a7c8d0 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -164,14 +164,14 @@ frame_callback(Dwfl_Frame *state, void *arg) } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct machine *machine, struct thread *thread, + struct thread *thread, struct perf_sample *data, int max_stack) { struct unwind_info ui = { .sample = data, .thread = thread, - .machine = machine, + .machine = thread->mg->machine, .cb = cb, .arg = arg, .max_stack = max_stack, diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 29acc8cccb56..371219a6daf1 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -592,14 +592,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct machine *machine, struct thread *thread, + struct thread *thread, struct perf_sample *data, int max_stack) { u64 ip; struct unwind_info ui = { .sample = data, .thread = thread, - .machine = machine, + .machine = thread->mg->machine, }; int ret; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index f50b737235eb..12790cf94618 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -16,7 +16,6 @@ typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); #ifdef HAVE_DWARF_UNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct machine *machine, struct thread *thread, struct perf_sample *data, int max_stack); /* libunwind specific */ @@ -38,7 +37,6 @@ static inline void unwind__finish_access(struct thread *thread __maybe_unused) { static inline int unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, - struct machine *machine __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, int max_stack __maybe_unused) -- cgit v1.2.3 From c00c48fc6e6ef63d83a7417923a06b08089bb34b Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 4 Nov 2014 10:14:27 +0900 Subject: perf symbols: Preparation for compressed kernel module support This patch adds basic support to handle compressed kernel module as some distro (such as Archlinux) carries on it now. The actual work using compression library will be added later. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415063674-17206-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dso.c | 75 ++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/dso.h | 7 +++++ tools/perf/util/machine.c | 19 ++++++++++- tools/perf/util/symbol-elf.c | 35 ++++++++++++++++++++- tools/perf/util/symbol.c | 8 ++++- 5 files changed, 141 insertions(+), 3 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 0247acfdfaca..36a607cf8f50 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -21,8 +21,10 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', + [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP] = 'm', [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__GUEST_KMODULE_COMP] = 'M', [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', }; @@ -112,11 +114,13 @@ int dso__read_binary_type_filename(const struct dso *dso, break; case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: path__join3(filename, size, symbol_conf.symfs, root_dir, dso->long_name); break; case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: __symbol__join_symfs(filename, size, dso->long_name); break; @@ -137,6 +141,77 @@ int dso__read_binary_type_filename(const struct dso *dso, return ret; } +static int decompress_dummy(const char *input __maybe_unused, + int output __maybe_unused) +{ + return -1; +} + +static const struct { + const char *fmt; + int (*decompress)(const char *input, int output); +} compressions[] = { + { "gz", decompress_dummy }, + { NULL, }, +}; + +bool is_supported_compression(const char *ext) +{ + unsigned i; + + for (i = 0; compressions[i].fmt; i++) { + if (!strcmp(ext, compressions[i].fmt)) + return true; + } + return false; +} + +bool is_kmodule_extension(const char *ext) +{ + if (strncmp(ext, "ko", 2)) + return false; + + if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3))) + return true; + + return false; +} + +bool is_kernel_module(const char *pathname, bool *compressed) +{ + const char *ext = strrchr(pathname, '.'); + + if (ext == NULL) + return false; + + if (is_supported_compression(ext + 1)) { + if (compressed) + *compressed = true; + ext -= 3; + } else if (compressed) + *compressed = false; + + return is_kmodule_extension(ext + 1); +} + +bool decompress_to_file(const char *ext, const char *filename, int output_fd) +{ + unsigned i; + + for (i = 0; compressions[i].fmt; i++) { + if (!strcmp(ext, compressions[i].fmt)) + return !compressions[i].decompress(filename, + output_fd); + } + return false; +} + +bool dso__needs_decompress(struct dso *dso) +{ + return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; +} + /* * Global list of open DSOs and the counter. */ diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index a316e4af321f..3782c82c6e44 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -22,7 +22,9 @@ enum dso_binary_type { DSO_BINARY_TYPE__BUILDID_DEBUGINFO, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__GUEST_KMODULE_COMP, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, DSO_BINARY_TYPE__KCORE, DSO_BINARY_TYPE__GUEST_KCORE, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, @@ -185,6 +187,11 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); +bool is_supported_compression(const char *ext); +bool is_kmodule_extension(const char *ext); +bool is_kernel_module(const char *pathname, bool *compressed); +bool decompress_to_file(const char *ext, const char *filename, int output_fd); +bool dso__needs_decompress(struct dso *dso); /* * The dso__data_* external interface provides following functions: diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 51a630301afa..946c7d62cb6e 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -464,6 +464,7 @@ struct map *machine__new_module(struct machine *machine, u64 start, { struct map *map; struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); + bool compressed; if (dso == NULL) return NULL; @@ -476,6 +477,11 @@ struct map *machine__new_module(struct machine *machine, u64 start, dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; else dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + + /* _KMODULE_COMP should be next to _KMODULE */ + if (is_kernel_module(filename, &compressed) && compressed) + dso->symtab_type++; + map_groups__insert(&machine->kmaps, map); return map; } @@ -861,8 +867,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, struct map *map; char *long_name; - if (dot == NULL || strcmp(dot, ".ko")) + if (dot == NULL) continue; + + /* On some system, modules are compressed like .ko.gz */ + if (is_supported_compression(dot + 1) && + is_kmodule_extension(dot - 2)) + dot -= 3; + snprintf(dso_name, sizeof(dso_name), "[%.*s]", (int)(dot - dent->d_name), dent->d_name); @@ -1044,6 +1056,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine, dot = strrchr(name, '.'); if (dot == NULL) goto out_problem; + /* On some system, modules are compressed like .ko.gz */ + if (is_supported_compression(dot + 1)) + dot -= 3; + if (!is_kmodule_extension(dot + 1)) + goto out_problem; snprintf(short_module_name, sizeof(short_module_name), "[%.*s]", (int)(dot - name), name); strxfrchar(short_module_name, '-', '_'); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 1e23a5bfb044..efc7eb6b8f0f 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -546,6 +546,35 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata) return 0; } +static int decompress_kmodule(struct dso *dso, const char *name, + enum dso_binary_type type) +{ + int fd; + const char *ext = strrchr(name, '.'); + char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; + + if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && + type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) || + type != dso->symtab_type) + return -1; + + if (!ext || !is_supported_compression(ext + 1)) + return -1; + + fd = mkstemp(tmpbuf); + if (fd < 0) + return -1; + + if (!decompress_to_file(ext + 1, name, fd)) { + close(fd); + fd = -1; + } + + unlink(tmpbuf); + + return fd; +} + bool symsrc__possibly_runtime(struct symsrc *ss) { return ss->dynsym || ss->opdsec; @@ -571,7 +600,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, Elf *elf; int fd; - fd = open(name, O_RDONLY); + if (dso__needs_decompress(dso)) + fd = decompress_kmodule(dso, name, type); + else + fd = open(name, O_RDONLY); + if (fd < 0) return -1; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 078331140d8c..c69915c9d5bc 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -51,7 +51,9 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__BUILDID_DEBUGINFO, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__GUEST_KMODULE_COMP, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -1300,7 +1302,9 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, return dso->kernel == DSO_TYPE_GUEST_KERNEL; case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: /* * kernel modules know their symtab type - it's set when * creating a module dso in machine__new_module(). @@ -1368,7 +1372,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) return -1; kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; /* * Iterate over candidate debug images. -- cgit v1.2.3 From b837a8bdc48925e6512412973b845c53cbe2b412 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 4 Nov 2014 10:14:33 +0900 Subject: perf tools: Fix build-id matching on vmlinux There's a problem on finding correct kernel symbols when perf report runs on a different kernel. Although a part of the problem was solved by the prior commit 0a7e6d1b6844 ("perf tools: Check recorded kernel version when finding vmlinux"), there's a remaining problem still. When perf records samples, it synthesizes the kernel map using machine__mmap_name() and ref_reloc_sym like "[kernel.kallsyms]_text". You can easily see it using 'perf report -D' command. After finishing record, it goes through the recorded events to find maps/dsos actually used. And then record build-id info of them. During this process, it needs to load symbols in a dso and it'd call dso__load_vmlinux_path() since the default value of the symbol_conf. try_vmlinux_path is true. However it changes dso->long_name to a real path of the vmlinux file (e.g. /lib/modules/3.16.4/build/vmlinux) if one is running on a custom kernel. It resulted in that perf report reads the build-id of the vmlinux, but cannot use it since it only knows about the [kernel.kallsyms] map. It then falls back to possible vmlinux paths by using the recorded kernel version (in case of a recent version) or a running kernel silently. Even with the recent tools, this still has a possibility of breaking the result. As the build directory is a symbolic link, if one built a new kernel in the same directory with different source/config, the old link to vmlinux will point the new file. So it's absolutely needed to use build-id when finding a kernel image. In this patch, it's now changed to try to search a kernel dso in the existing dso list which was constructed during build-id table parsing so it'll always have a build-id. If not found, search "[kernel.kallsyms]". Before: $ perf report # Children Self Command Shared Object Symbol # ........ ........ ....... ................. ............................... # 72.15% 0.00% swapper [kernel.kallsyms] [k] set_curr_task_rt 72.15% 0.00% swapper [kernel.kallsyms] [k] native_calibrate_tsc 72.15% 0.00% swapper [kernel.kallsyms] [k] tsc_refine_calibration_work 71.87% 71.87% swapper [kernel.kallsyms] [k] module_finalize ... After (for the same perf.data): 72.15% 0.00% swapper vmlinux [k] cpu_startup_entry 72.15% 0.00% swapper vmlinux [k] arch_cpu_idle 72.15% 0.00% swapper vmlinux [k] default_idle 71.87% 71.87% swapper vmlinux [k] native_safe_halt ... Signed-off-by: Namhyung Kim Acked-by: Ingo Molnar Link: http://lkml.kernel.org/r/20140924073356.GB1962@gmail.com Cc: Adrian Hunter Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415063674-17206-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/header.c | 2 +- tools/perf/util/machine.c | 16 ++++++++++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 3e2c156d9c64..76442caca37e 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1269,7 +1269,7 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (filename[0] == '[') + if (!is_kernel_module(filename, NULL)) dso->kernel = dso_type; build_id__sprintf(dso->build_id, sizeof(dso->build_id), diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 946c7d62cb6e..53f90e9c65fe 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1085,8 +1085,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine, * Should be there already, from the build-id table in * the header. */ - struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, - kmmap_prefix); + struct dso *kernel = NULL; + struct dso *dso; + + list_for_each_entry(dso, &machine->kernel_dsos.head, node) { + if (is_kernel_module(dso->long_name, NULL)) + continue; + + kernel = dso; + break; + } + + if (kernel == NULL) + kernel = __dsos__findnew(&machine->kernel_dsos, + kmmap_prefix); if (kernel == NULL) goto out_problem; -- cgit v1.2.3 From 96d78059d6d9da45d77078a219924304860497f2 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 4 Nov 2014 10:14:34 +0900 Subject: perf tools: Make vmlinux short name more like kallsyms short name The previous patch changed kernel dso name from '[kernel.kallsyms]' to vmlinux. However it might add confusion to old users accustomed to the old name. So change the short name to '[kernel.vmlinux]' to reduce such confusion. Before: # Overhead Command Shared Object Symbol # ........ .............. ....................... ............................... # 9.83% swapper vmlinux [k] intel_idle 4.10% awk libc-2.20.so [.] __strcmp_sse2 1.86% sed libc-2.20.so [.] __strcmp_sse2 1.78% netctl-auto libc-2.20.so [.] __strcmp_sse2 1.23% netctl-auto libc-2.20.so [.] __mbrtowc 1.21% firefox libxul.so [.] 0x00000000024b62bd 1.20% swapper vmlinux [k] cpuidle_enter_state 1.03% sleep vmlinux [k] copy_user_generic_unrolled After: # Overhead Command Shared Object Symbol # ........ .............. ....................... ............................... # 9.83% swapper [kernel.vmlinux] [k] intel_idle 4.10% awk libc-2.20.so [.] __strcmp_sse2 1.86% sed libc-2.20.so [.] __strcmp_sse2 1.78% netctl-auto libc-2.20.so [.] __strcmp_sse2 1.23% netctl-auto libc-2.20.so [.] __mbrtowc 1.21% firefox libxul.so [.] 0x00000000024b62bd 1.20% swapper [kernel.vmlinux] [k] cpuidle_enter_state 1.03% sleep [kernel.vmlinux] [k] copy_user_generic_unrolled Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1415063674-17206-9-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 53f90e9c65fe..52e94902afb1 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1106,6 +1106,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (__machine__create_kernel_maps(machine, kernel) < 0) goto out_problem; + if (strstr(dso->long_name, "vmlinux")) + dso__set_short_name(dso, "[kernel.vmlinux]", false); + machine__set_kernel_mmap_len(machine, event); /* -- cgit v1.2.3 From 37592b8afb7151994e760d1727c264329d9c13c8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:19 -0800 Subject: perf callchain: Factor out adding new call chain entries Move the code to resolve and add a new callchain entry into a new add_callchain_ip function. This will be used in the next patches to add LBRs too. No change in behavior. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-2-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 51 +++++++++++++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 19 deletions(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 52e94902afb1..84390eecab06 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1381,6 +1381,34 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, return mi; } +static int add_callchain_ip(struct thread *thread, + struct symbol **parent, + struct addr_location *root_al, + int cpumode, + u64 ip) +{ + struct addr_location al; + + al.filtered = 0; + al.sym = NULL; + thread__find_addr_location(thread, cpumode, MAP__FUNCTION, + ip, &al); + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + symbol__match_regex(al.sym, &parent_regex)) + *parent = al.sym; + else if (have_ignore_callees && root_al && + symbol__match_regex(al.sym, &ignore_callees_regex)) { + /* Treat this symbol as the root, + forgetting its callees. */ + *root_al = al; + callchain_cursor_reset(&callchain_cursor); + } + } + + return callchain_cursor_append(&callchain_cursor, ip, al.map, al.sym); +} + struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al) { @@ -1427,7 +1455,6 @@ static int thread__resolve_callchain_sample(struct thread *thread, for (i = 0; i < chain_nr; i++) { u64 ip; - struct addr_location al; if (callchain_param.order == ORDER_CALLEE) j = i; @@ -1464,24 +1491,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, continue; } - al.filtered = 0; - thread__find_addr_location(thread, cpumode, - MAP__FUNCTION, ip, &al); - if (al.sym != NULL) { - if (sort__has_parent && !*parent && - symbol__match_regex(al.sym, &parent_regex)) - *parent = al.sym; - else if (have_ignore_callees && root_al && - symbol__match_regex(al.sym, &ignore_callees_regex)) { - /* Treat this symbol as the root, - forgetting its callees. */ - *root_al = al; - callchain_cursor_reset(&callchain_cursor); - } - } - - err = callchain_cursor_append(&callchain_cursor, - ip, al.map, al.sym); + err = add_callchain_ip(thread, parent, root_al, + cpumode, ip); + if (err == -EINVAL) + break; if (err) return err; } -- cgit v1.2.3 From 5550171b2a9f8df26ff483051d060db06376b26d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 12 Nov 2014 18:05:21 -0800 Subject: perf callchain: Use al.addr to set up call chain Use the relative address, this makes get_srcline work correctly in the end. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1415844328-4884-4-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/machine.c') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 84390eecab06..d97309c87bd6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1406,7 +1406,7 @@ static int add_callchain_ip(struct thread *thread, } } - return callchain_cursor_append(&callchain_cursor, ip, al.map, al.sym); + return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, -- cgit v1.2.3